From f4accfe9592cdcbf72aceb63c45c452453f0e3e4 Mon Sep 17 00:00:00 2001 From: Cameron Blankenbuehler Date: Wed, 28 Sep 2022 13:01:39 -0400 Subject: [PATCH] Update wordlist splitting script - use ripgrep to exclude proper nouns (with capitals) output only the capture group --- src/boggler/split_wordlist_en.sh | 52 ++++++++++++++++---------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/src/boggler/split_wordlist_en.sh b/src/boggler/split_wordlist_en.sh index 0fa8913..692ae43 100755 --- a/src/boggler/split_wordlist_en.sh +++ b/src/boggler/split_wordlist_en.sh @@ -4,32 +4,32 @@ if [ -z $1 ] || [ -z $2 ]; then echo "Usage: WORDLIST OUT_DIR" exit 0 else - grep -ioP "^a[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_a.txt" - grep -ioP "^b[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_b.txt" - grep -ioP "^c[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_c.txt" - grep -ioP "^d[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_d.txt" - grep -ioP "^e[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_e.txt" - grep -ioP "^f[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_f.txt" - grep -ioP "^g[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_g.txt" - grep -ioP "^h[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_h.txt" - grep -ioP "^i[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_i.txt" - grep -ioP "^j[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_j.txt" - grep -ioP "^k[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_k.txt" - grep -ioP "^l[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_l.txt" - grep -ioP "^m[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_m.txt" - grep -ioP "^n[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_n.txt" - grep -ioP "^o[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_o.txt" - grep -ioP "^p[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_p.txt" - grep -ioP "^q[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_q.txt" - grep -ioP "^r[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_r.txt" - grep -ioP "^s[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_s.txt" - grep -ioP "^t[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_t.txt" - grep -ioP "^u[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_u.txt" - grep -ioP "^v[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_v.txt" - grep -ioP "^w[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_w.txt" - grep -ioP "^x[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_x.txt" - grep -ioP "^y[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_y.txt" - grep -ioP "^z[a-z]+" $1 | tr [A-Z] [a-z] | sort | uniq > "$2/words_z.txt" + rg "(^a[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_a.txt" + rg "(^b[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_b.txt" + rg "(^c[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_c.txt" + rg "(^d[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_d.txt" + rg "(^e[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_e.txt" + rg "(^f[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_f.txt" + rg "(^g[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_g.txt" + rg "(^h[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_h.txt" + rg "(^i[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_i.txt" + rg "(^j[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_j.txt" + rg "(^k[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_k.txt" + rg "(^l[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_l.txt" + rg "(^m[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_m.txt" + rg "(^n[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_n.txt" + rg "(^o[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_o.txt" + rg "(^p[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_p.txt" + rg "(^q[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_q.txt" + rg "(^r[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_r.txt" + rg "(^s[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_s.txt" + rg "(^t[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_t.txt" + rg "(^u[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_u.txt" + rg "(^v[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_v.txt" + rg "(^w[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_w.txt" + rg "(^x[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_x.txt" + rg "(^y[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_y.txt" + rg "(^z[a-z]+).*$" -or '$1' $1 | sort | uniq > "$2/words_z.txt" touch "$2/words__.txt" exit 0 fi